TFS-ViT: Token-Level Feature Stylization for Domain Generalization

arXiv:2303.15698v3 Announce Type: replace
Abstract: Standard deep learning models such as convolutional neural networks (CNNs) lack the ability of generalizing to domains which have not been seen during training. This problem is mainly due to the common but often wrong assumption of such models that the source and target data come from the same i.i.d. distribution. Recently, Vision Transformers (ViTs) have shown outstanding performance for a broad range of computer vision tasks. However, very few studies have investigated their ability …

arxiv cs.cv domain feature token type vit